# A Diffusion-Based Framework for High-Resolution Precipitation Forecasting over CONUS

arXiv: https://arxiv.org/abs/2512.09059 · HTML: https://mlsanity.com/paper/2512.09059/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 53 references that are in the map.
- First posted on arXiv 9 Dec 2025.

## Builds on (most cited first, 11 of 11)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting](https://mlsanity.com/paper/1506.04214/) (2015)
- [Deep learning to represent sub-grid processes in climate models](https://mlsanity.com/paper/1806.04731/) (2018)
- [MetNet: A Neural Weather Model for Precipitation Forecasting](https://mlsanity.com/paper/2003.12140/) (2020)
- [Residual Corrective Diffusion Modeling for Km-scale Atmospheric Downscaling](https://mlsanity.com/paper/2309.15214/) (2023)
- [Deep Learning for Day Forecasts from Sparse Observations](https://mlsanity.com/paper/2306.06079/) (2023)
- [Precipitation nowcasting with generative diffusion models](https://mlsanity.com/paper/2308.06733/) (2023)
- [Unmasking Bias in Diffusion Model Training](https://mlsanity.com/paper/2310.08442/) (2023)
- [How to use score-based diffusion in earth system science: A satellite nowcasting example](https://mlsanity.com/paper/2505.10432/) (2025)
- [A Multi-Modal Machine Learning Approach to Detect Extreme Rainfall Events in Sicily](https://mlsanity.com/paper/2212.08102/) (2022)

## Built on by (most cited first, 2 of 2)

- [Diffusion-Based Rollouts as a Stabilization Mechanism for Long-Horizon Environmental Forecasting](https://mlsanity.com/paper/2609.33930/) (2026)
- [RainAtlas: A Multi-Continental Dataset for Precipitation Downscaling](https://mlsanity.com/paper/2609.39833/) (2026)

## Abstract (arXiv)

Accurate precipitation forecasting is essential for hydrometeorological risk management, especially for anticipating extreme rainfall that can lead to flash flooding and infrastructure damage. This study introduces a diffusion-based deep learning (DL) framework that systematically compares three residual prediction strategies differing only in their input sources: (1) a fully data-driven model using only past observations from the Multi-Radar Multi-Sensor (MRMS) system, (2) a corrective model using only forecasts from the High-Resolution Rapid Refresh (HRRR) numerical weather prediction system, and (3) a hybrid model integrating both MRMS and selected HRRR forecast variables. By evaluating these approaches under a unified setup, we provide a clearer understanding of how each data source contributes to predictive skill over the Continental United States (CONUS). Forecasts are produced at 1-km spatial resolution, beginning with direct 1-hour predictions and extending to 12 hours using autoregressive rollouts. Performance is evaluated using both CONUS-wide and region-specific metrics that assess overall performance and skill at extreme rainfall thresholds. Across all lead times, our DL framework consistently outperforms the HRRR baseline in pixel-wise and spatiostatistical metrics. The hybrid model performs best at the shortest lead time, while the HRRR-corrective model outperforms others at longer lead times, maintaining high skill through 12 hours. To assess reliability, we incorporate calibrated uncertainty quantification tailored to the residual learning setup. These gains, particularly at longer lead times, are critical for emergency preparedness, where modest increases in forecast horizon can improve decision-making. This work advances DL-based precipitation forecasting by enhancing predictive skill, reliability, and applicability across regions.